Copertina

SAIL: Self-Improving Efficient Online Alignment of Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ding, Mucong, Chakraborty, Souradip, Agrawal, Vibhu, Che, Zora, Koppel, Alec, Wang, Mengdi, Bedi, Amrit, Huang, Furong
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MaxMin-RLHF: Alignment with Diverse Human Preferences
di: Chakraborty, Souradip, et al.
Pubblicazione: (2024)

LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds
di: Beetham, James, et al.
Pubblicazione: (2024)

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
di: Chakraborty, Souradip, et al.
Pubblicazione: (2023)

Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
di: Agrawal, Aakriti, et al.
Pubblicazione: (2025)

Transfer Q Star: Principled Decoding for LLM Alignment
di: Chakraborty, Souradip, et al.
Pubblicazione: (2024)

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
di: Agrawal, Aakriti, et al.
Pubblicazione: (2025)

Code Comprehension then Auditing for Unsupervised LLM Evaluation
di: Patel, Bhrij, et al.
Pubblicazione: (2024)

Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
di: Ghosal, Soumya Suvra, et al.
Pubblicazione: (2026)

Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
di: Chakraborty, Souradip, et al.
Pubblicazione: (2025)

Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models
di: Ghosal, Soumya Suvra, et al.
Pubblicazione: (2025)

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
di: Agrawal, Aakriti, et al.
Pubblicazione: (2024)

Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
di: Chehade, Mohamad, et al.
Pubblicazione: (2025)

PROPS: Progressively Private Self-alignment of Large Language Models
di: Teku, Noel, et al.
Pubblicazione: (2025)

GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment
di: Xu, Yuancheng, et al.
Pubblicazione: (2024)

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
di: Ghosal, Soumya Suvra, et al.
Pubblicazione: (2024)

On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows
di: Chakraborty, Souradip, et al.
Pubblicazione: (2025)

Auction-Based Regulation for Artificial Intelligence
di: Bornstein, Marco, et al.
Pubblicazione: (2024)

MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models
di: Zhai, Kevin, et al.
Pubblicazione: (2025)

Efficient Alignment of Large Language Models via Data Sampling
di: Khera, Amrit, et al.
Pubblicazione: (2024)

Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks
di: Sun, Xingpeng, et al.
Pubblicazione: (2024)

RL with Learnable Textual Feedback: A Bilevel Approach
di: Singh, Utsav, et al.
Pubblicazione: (2026)

Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training
di: Barakat, Anas, et al.
Pubblicazione: (2026)

Is poisoning a real threat to LLM alignment? Maybe more so than you think
di: Pathmanathan, Pankayaraj, et al.
Pubblicazione: (2024)

BalancedDPO: Adaptive Multi-Metric Alignment
di: Tamboli, Dipesh, et al.
Pubblicazione: (2025)

Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
di: Panaitescu-Liess, Michael-Andrei, et al.
Pubblicazione: (2024)

Post-training Large Language Models for Diverse High-Quality Responses
di: Chen, Yilei, et al.
Pubblicazione: (2025)

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
di: Trivedi, Prashant, et al.
Pubblicazione: (2025)

VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences
di: Singh, Anukriti, et al.
Pubblicazione: (2025)

On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
di: Barakat, Anas, et al.
Pubblicazione: (2024)

Agentic Critical Training
di: Liu, Weize, et al.
Pubblicazione: (2026)

SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
di: Ding, Mucong, et al.
Pubblicazione: (2024)

Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling
di: Pathmanathan, Pankayaraj, et al.
Pubblicazione: (2025)

Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models
di: Ji, Xiang, et al.
Pubblicazione: (2024)

Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning
di: Yu, Peihong, et al.
Pubblicazione: (2024)

Improving and Assessing the Fidelity of Large Language Models Alignment to Online Communities
di: Chu, Minh Duc, et al.
Pubblicazione: (2024)

Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
di: Ding, Mucong, et al.
Pubblicazione: (2024)

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
di: Wang, Xiyao, et al.
Pubblicazione: (2024)

Active Preference Optimization for Sample Efficient RLHF
di: Das, Nirjhar, et al.
Pubblicazione: (2024)

FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
di: Bornstein, Marco, et al.
Pubblicazione: (2024)

Spectral Greedy Coresets for Graph Neural Networks
di: Ding, Mucong, et al.
Pubblicazione: (2024)